Publication:
Subspace Detection Approaches for Hyperspectral Image Classification

dc.contributor.advisor Jia, Dr Xiuping en_US
dc.contributor.advisor Pickering, Dr Mark en_US
dc.contributor.author Hossain, Md Ali en_US
dc.date.accessioned 2022-03-15T10:46:35Z
dc.date.available 2022-03-15T10:46:35Z
dc.date.issued 2014 en_US
dc.description.abstract Hyperspectral data provides rich information and is very useful for a range of applications from ground-cover types identification to target detection. With many benefits they also present some challenges including high storage cost, intensive computational load and difficulties in machine assisted interpretation, namely, in classification. The limited number of training samples may cause a significant loss in classification accuracy. This thesis investigates effective and feasible approaches to reduce the dimensionality of the hyperspectral images while keeping the intrinsic structure of the input data intact. The first study is concerned with finding a subspace which consists of the most informative features for reliable hyperspectral image classification. In this study, a hybrid approach which combines both feature extraction and feature selection is proposed. Principal Component Analysis (PCA) is applied first to generate new features from the complete set of the original spectral bands. Feature selection is then performed effectively using a normalized mutual information measure with two constraints to maximize the general relevance and minimize redundancy to the target class identification in the selected subspace. Improvement of the existing nonlinear feature extraction method is undertaken in the second study. In this study, the input features are decorrelated at the first step by applying nonlinear kernel principal component analysis. The spatial properties of the input features are then incorporated to select a subset of features which better reveal object structures and provide good separation among the classes of interest. The third contribution of this study is the evaluation of a number of recent approaches for kernel selection and an improved and computationally efficient approach is proposed. The alignment between the target kernel matrix and input kernel matrix is used to select the kernel parameter(s) for each candidate kernel function. Cross-validation is used at the final stage to search for the best kernel function using the selected kernel parameter(s) for each function. Experiments were carried out on both real and synthetic data. The results show that the proposed approaches provide an improved classification performance. en_US
dc.identifier.uri http://hdl.handle.net/1959.4/53507
dc.language English
dc.language.iso EN en_US
dc.publisher UNSW, Sydney en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/3.0/au/ en_US
dc.subject.other Feature selection en_US
dc.subject.other Image classification en_US
dc.subject.other Feature extraction en_US
dc.subject.other Mutual Information en_US
dc.subject.other Hyperspectral image en_US
dc.subject.other Feature reduction en_US
dc.title Subspace Detection Approaches for Hyperspectral Image Classification en_US
dc.type Thesis en_US
dcterms.accessRights open access
dcterms.rightsHolder Hossain, Md Ali
dspace.entity.type Publication en_US
unsw.accessRights.uri https://purl.org/coar/access_right/c_abf2
unsw.date.embargo 2015-06-12 en_US
unsw.description.embargoNote Embargoed until 2015-06-12
unsw.identifier.doi https://doi.org/10.26190/unsworks/2565
unsw.relation.faculty UNSW Canberra
unsw.relation.originalPublicationAffiliation Hossain, Md Ali, Engineering & Information Technology, UNSW Canberra, UNSW en_US
unsw.relation.originalPublicationAffiliation Jia, Dr Xiuping, Engineering & Information Technology, UNSW Canberra, UNSW en_US
unsw.relation.originalPublicationAffiliation Pickering, Dr Mark , Engineering & Information Technology, UNSW Canberra, UNSW en_US
unsw.relation.school School of Engineering and Information Technology *
unsw.thesis.degreetype PhD Doctorate en_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
public version.pdf
Size:
5.28 MB
Format:
application/pdf
Description:
Resource type